Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery

We propose a new convolutional neural networks method in combination with ordinal regression aiming at assessing the degree of building damage caused by earthquakes with aerial imagery. The ordinal regression model and a deep learning algorithm are incorporated to make full use of the information to improve the accuracy of the assessment. A new loss function was introduced in this paper to combine convolutional neural networks and ordinal regression. Assessing the level of damage to buildings can be considered as equivalent to predicting the ordered labels of buildings to be assessed. In the existing research, the problem has usually been simplified as a problem of pure classification to be further studied and discussed, which ignores the ordinal relationship between different levels of damage, resulting in a waste of information. Data accumulated throughout history are used to build network models for assessing the level of damage, and models for assessing levels of damage to buildings based on deep learning are described in detail, including model construction, implementation methods, and the selection of hyperparameters, and verification is conducted by experiments. When categorizing the damage to buildings into four types, we apply the method proposed in this paper to aerial images acquired from the 2014 Ludian earthquake and achieve an overall accuracy of 77.39%; when categorizing damage to buildings into two types, the overall accuracy of the model is 93.95%, exceeding such values in similar types of theories and methods. a set of 13 change detention features and support vector machine (SVM). Simon Plank [12] reviewed the methods of rapid damage assessment using multitemporal Synthetic Aperture Radar(SAR) data. Gupta et al. [13] present a satellite imagery dataset for building damage assessment with over 700,000 labeled building instances covering over 5000 km 2 of imagery.Recent studies show that the machine learning algorithm performs well in earthquake damage assessment. Li [14] assessed building damage with one-class SVM using pre-and post-earthquake QuickBird imagery and assessed the discrimination power of different level (pixel-level, texture, and object-based) features. Haiyang et al. [15] combined SVM and the image segmentation method to detect building damage. Cooner et al. [16] evaluate the effectiveness of machine learning algorithms in detecting earthquake damage. A series of textural and structural features were used in this study. A SVM and feature selection approach was carried out for damage mapping with post-event very high spatial resolution(VHR) image and obtained overall accuracy (OA) of 96.8% and Kappa of 0.5240 [11]. Convolutional neural networks (CNN) was utilized to identify collapsed buildings from post-event satellite imagery and obtained an OA of 80.1% and Kappa of 0.46 [17]. Multiresolution feature maps were derived and fused with CNN for the image classification of building damages in [18], and an OA of 88.7% was obtained.Most of the above-mentioned damage information extracti...

Section: Ordinal Regressionmentioning

confidence: 99%

Assessment of the Degree of Building Damage Caused by Disaster Using Convolutional Neural Networks in Combination with Ordinal Regression

Liu

Wang

2019

“…Machine learning techniques, Random Forest (RF) [82][83][84][85] and Naïve Bayes were further utilized to classify and provide greater clarity to the feature distribution. The RF technique, which was found to yield the clearest results, is a nonparametric method for modelling the continuous and discrete data of decision tree methods and is a well-established and reliable process [86][87][88]. However, quantitative characterization of the inputs passed to the model must be rigidly applied, and factors such as the uncertainty of the data taken into account in order to prevent overfitting and incorrect outcomes [89][90][91].…”

Section: Advanced Processingmentioning

confidence: 99%

Mapping Heterogeneous Buried Archaeological Features Using Multisensor Data from Unmanned Aerial Vehicles

Brooke

Clutterbuck

2019

There is a long history of the use of aerial imagery for archaeological research, but the application of multisensor image data has only recently been facilitated by the development of unmanned aerial vehicles (UAVs). Two archaeological sites in the East Midlands U.K. that differ in age and topography were selected for survey using multisensor imaging from a fixed-wing UAV. The aim of this study was to determine optimum methodology for the use of UAVs in examining archaeological sites that have no obvious surface features and examine issues of ground control target design, thermal effects, image processing and advanced filtration. The information derived from the range of sensors used in this study enabled interpretation of buried archaeology at both sites. For any archaeological survey using UAVs, the acquisition of visible colour (RGB), multispectral, and thermal imagery as a minimum are advised, as no single technique is sufficient to attempt to reveal the maximum amount of potential information.

“…They generally occur when the training data are not evenly distributed across all classes and concentrated on a certain few classes. If such issues exist, the overall accuracy for the model performance might be diminished because rare classes are not adequately trained [69,70]. The class imbalance issue is common in many real-world applications [71], including ocean color data.…”

Section: Data Preprocessingmentioning

confidence: 99%

Reconstruction of Ocean Color Data Using Machine Learning Techniques in Polar Regions: Focusing on Off Cape Hallett, Ross Sea

Park

Kim

et al. 2019

The most problematic issue in the ocean color application is the presence of heavy clouds, especially in polar regions. For that reason, the demand for the ocean color application in polar regions is increased. As a way to overcome such issues, we conducted the reconstruction of the chlorophyll-a concentration (CHL) data using the machine learning-based models to raise the usability of CHL data. This analysis was first conducted on a regional scale and focused on the biologically-valued Cape Hallett, Ross Sea, Antarctica. Environmental factors and geographical information associated with phytoplankton dynamics were considered as predictors for the CHL reconstruction, which were obtained from cloud-free microwave and reanalysis data. As the machine learning models used in the present study, the ensemble-based models such as Random forest (RF) and Extremely randomized tree (ET) were selected with 10-fold cross-validation. As a result, both CHL reconstructions from the two models showed significant agreement with the standard satellite-derived CHL data. In addition, the reconstructed CHLs were close to the actual CHL value even where it was not observed by the satellites. However, there is a slight difference between the CHL reconstruction results from the RF and the ET, which is likely caused by the difference in the contribution of each predictor. In addition, we examined the variable importance for the CHL reconstruction quantitatively. As such, the sea surface and atmospheric temperature, and the photosynthetically available radiation have high contributions to the model developments. Mostly, geographic information appears to have a lower contribution relative to environmental predictors. Lastly, we estimated the partial dependences for the predictors for further study on the variable contribution and investigated the contributions to the CHL reconstruction with changes in the predictors.